Senior AI Engineer - Agentic Systems in Production

Centrica plc; Windsor; Hybrid; CAD 159,000 - 225,000; Full time

Job summary

Centrica plc in the UK is seeking a Senior AI Engineer to own the intelligence layer of our agentic products across voice, chat and email channels. You will design and deploy advanced AI services with Bedrock, AgentCore Runtime, and retrieval-augmented generation, balancing performance, safety and governance.

You will implement multi-step orchestration, manage conversational state, and measure accuracy and containment with a formal evaluation harness, working with Terraform, CI/CD and cloud

Qualifications

• Substantial software engineering experience with strong Python.
• Proven delivery of LLM/agentic systems to production with real users.
• Hands-on experience with tool and function calling, multi-step agent orchestration, and managing conversational state across turns.
• Experience with retrieval-augmented generation and evaluation harness.
• Cloud AI services deployment using serverless or containers and IaC like Terraform, with CI/CD.

Responsibilities

• Design and build agentic services on Bedrock and AgentCore Runtime.
• Implement multi-step orchestration, state and memory management, and failure handling.
• Develop retrieval-augmented generation with content prep, embedding strategy, and grounding.
• Define evaluation metrics (accuracy, containment, safety) and governance reviews.
• Ensure latency, cost, and guardrails; monitor in production with observability tools.
• Document build-vs-buy decisions and architecture records for governance.

Skills

Python

LLM/agentic systems

Production code

Multi-step orchestration

Cloud deployments

CI/CD

Education

Bachelor's degree in CS/Engineering

Tools

Bedrock

AgentCore Runtime

Terraform

CI/CD pipelines

Job description

Centrica plc in the UK is seeking a Senior AI Engineer to own the intelligence layer of our agentic products across voice, chat and email channels. You will design and deploy advanced AI services with Bedrock, AgentCore Runtime, and retrieval-augmented generation, balancing performance, safety and governance.

You will implement multi-step orchestration, manage conversational state, and measure accuracy and containment with a formal evaluation harness, working with Terraform, CI/CD and cloud